Methods and Systems for Identifying Vehicles of Interest

Abstract

A method for identifying a vehicle of interest includes: accessing data corresponding to a vehicle of interest alert; accessing data from a sensor corresponding to images of one or more other vehicles; computing, with a machine-learned model, a vehicle of interest match estimate for the one or more other vehicles based at least in part on the data from the sensor; and computing a vehicle of interest identification.

What is claimed is: 
     
         1 . A method for identifying a vehicle of interest, comprising:
 accessing, with a computing device on a vehicle, data corresponding to a vehicle of interest alert;   accessing, with the computing device, data from a sensor corresponding to images of one or more other vehicles;   computing, with a machine-learned model on the computing device, a vehicle of interest match estimate for the one or more other vehicles based at least in part on the data from the sensor;   computing, with the computing device, a vehicle of interest identification in response to the vehicle of interest match estimate exceeding a threshold level; and   transmitting, with the computing device, data corresponding to the vehicle of interest identification to a remote computing device that is located outside the vehicle.   
     
     
         2 . The method of  claim 1 , wherein the vehicle of interest alert is issued by an emergency services agency. 
     
     
         3 . The method of  claim 1 , wherein the vehicle of interest alert comprises data corresponding to one or more of a make, a model, a color, and a license plate number for the vehicle of interest. 
     
     
         4 . The method of  claim 1 , wherein the sensor comprises one or more of an advanced driver assistance system camera, a backup camera, and a sideview camera. 
     
     
         5 . The method of  claim 1 , wherein the vehicle of interest match corresponds to a likelihood calculated by the machine-learned model that the one or more other vehicles matches the vehicle of interest. 
     
     
         6 . The method of  claim 1 , wherein the machine-learned model has been trained using a training dataset determined using information describing previous vehicles, the training dataset comprising one or more positive samples, each positive sample representing a vehicle identification characteristic. 
     
     
         7 . The method of  claim 6 , wherein the vehicle identification characteristic comprises one or more of a make, a model, a color, and a license plate number. 
     
     
         8 . The method of  claim 1 , wherein the vehicle of interest identification comprises one or more of:
 a location of the vehicle of interest;   a travel direction for the vehicle of interest;   a speed of the vehicle of interest; and   an image of the vehicle of interest.   
     
     
         9 . The method of  claim 1 , wherein the remote computing device comprises a cloud server, the method further comprising transmitting, with the cloud server, the vehicle of interest identification to an emergency services agency. 
     
     
         10 . The method of  claim 1 , further comprising computing, with the computing device, whether the vehicle is within a geofence for the vehicle of interest alert, wherein accessing the data from the sensor comprises accessing the data from the sensor when the vehicle is within the geofence. 
     
     
         11 . The method of  claim 10 , further comprising:
 accessing, with the computing device, data corresponding to an updated vehicle of interest alert;   computing, with the computing device, whether the vehicle is within an updated geofence for the updated vehicle of interest alert; and   continuing to access the data from the sensor when the vehicle is within the updated geofence.   
     
     
         12 . The method of  claim 10 , further comprising terminating the computing of the vehicle of interest match estimate when the vehicle is outside of the geofence. 
     
     
         13 . A system for identifying a vehicle of interest, comprising:
 a vehicle;   a sensor located on the vehicle;   one or more processors located onboard the vehicle; and   one or more non-transitory computer-readable media that store instructions that are executable by the one or more processors to perform operations, the operations comprising
 accessing data corresponding to a vehicle of interest alert, 
 accessing data from the sensor corresponding to images of one or more other vehicles, 
 computing, with a machine-learned model, a vehicle of interest match estimate for the one or more other vehicles based at least in part on the data from the sensor, 
 computing a vehicle of interest identification in response to the vehicle of interest match estimate exceeding a threshold level, and 
 transmitting data corresponding to the vehicle of interest identification to a remote computing device that is located outside the vehicle. 
   
     
     
         14 . The system of  claim 13 , wherein the vehicle of interest alert comprises data corresponding to one or more of a make, a model, a color, and a license plate number for the vehicle of interest. 
     
     
         15 . The system of  claim 13 , wherein the sensor comprises one or more of an advanced driver assistance system camera, a backup camera, and a sideview camera. 
     
     
         16 . The system of  claim 13 , wherein the vehicle of interest match corresponds to a likelihood calculated by the machine-learned model that the one or more other vehicles matches the vehicle of interest. 
     
     
         17 . The system of  claim 13 , wherein the vehicle of interest identification comprises one or more of:
 a location of the vehicle of interest;   a travel direction for the vehicle of interest;   a speed of the vehicle of interest; and   an image of the vehicle of interest.   
     
     
         18 . The system of  claim 13 , wherein the operations comprise computing whether the vehicle is within a geofence for the vehicle of interest alert, wherein accessing the data from the sensor comprises accessing the data from the sensor when the vehicle is within the geofence. 
     
     
         19 . The system of  claim 18 , wherein the operations comprise:
 accessing data corresponding to an updated vehicle of interest alert;   computing whether the vehicle is within an updated geofence for the updated vehicle of interest alert; and   continuing to access the data from the sensor when the vehicle is within the updated geofence.   
     
     
         20 . The system of  claim 18 , wherein the operations comprise terminating the computing of the vehicle of interest match estimate when the vehicle is outside of the geofence.